Yang Zheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yang Zheng has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Yu Wen
Chinese Academy of Sciences
2 shared publications - Bo Luo
The University of Kansas, Lawrence, KS, USA
1 shared publication - Boyang Zhang
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
1 shared publication - Dan Meng
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
1 shared publication - Gang Li
Deakin University
1 shared publication - Qizhou Peng1 shared publication
Latest Publications
- Open Access
Neutral Agent-based Adversarial Policy Learning against Deep Reinforcement Learning in Multi-party Open Systems
Reinforcement learning (RL) has been an important machine learning paradigm for solving long-horizon sequential decision-making problems under uncertainty. By integrating deep neural networks (DNNs) into the RL framework, deep reinforcement learning (DRL) has emerged, which achieved significant success in various domains. However, the integration of DNNs also makes it vulnerable to adversarial attacks. Existing adversarial attack techniques mainly focus on either directly manipulating the environment with which a victim agent interacts or deploying an adversarial agent that interacts with the victim agent to induce abnormal behaviors. While these techniques achieve promising results, their adoption in multi-party open systems remains limited due to two major reasons: impractical assumption of full control over the environment and dependent on interactions with victim agents. To enable adversarial attacks in multi-party open systems, in this paper, we redesigned an adversarial policy learning approach that can mislead well-trained victim agents without requiring direct interactions with these agents or full control over their environments. Particularly, we propose a neutral agent-based approach across various task scenarios in multi-party open systems. While the neutral agents seemingly are detached from the victim agents, indirectly influence them through the shared environment. We evaluate our proposed method on the SMAC platform based on Starcraft II and the autonomous driving simulation platform Highway-env. The experimental results demonstrate that our method can launch general and effective adversarial attacks in multi-party open systems.
Open AccessNeutral Agent-based Adversarial Policy Learning against Deep Reinforcement Learning in Multi-party Open Systems
Reinforcement learning (RL) has been an important machine learning paradigm for solving long-horizon sequential decision-making problems under uncertainty. By integrating deep neural networks (DNNs) into the RL framework, deep reinforcement learning (DRL) has emerged, which achieved significant success in various domains. However, the integration of DNNs also makes it vulnerable to adversarial attacks. Existing adversarial attack techniques mainly focus on either directly manipulating the environment with which a victim agent interacts or deploying an adversarial agent that interacts with the victim agent to induce abnormal behaviors. While these techniques achieve promising results, their adoption in multi-party open systems remains limited due to two major reasons: impractical assumption of full control over the environment and dependent on interactions with victim agents. To enable adversarial attacks in multi-party open systems, in this paper, we redesigned an adversarial policy learning approach that can mislead well-trained victim agents without requiring direct interactions with these agents or full control over their environments. Particularly, we propose a neutral agent-based approach across various task scenarios in multi-party open systems. While the neutral agents seemingly are detached from the victim agents, indirectly influence them through the shared environment. We evaluate our proposed method on the SMAC platform based on Starcraft II and the autonomous driving simulation platform Highway-env. The experimental results demonstrate that our method can launch general and effective adversarial attacks in multi-party open systems.
- 8 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 20 (2) , 1104-1123
SparkAC: Fine-Grained Access Control in Spark for Secure Data Sharing and Analytics
With the development of computing and communication technologies, an extremely large amount of data has been collected, stored, utilized, and shared, while new security and privacy challenges arise. Existing access control mechanisms provided by big data platforms have limitations in granularity and expressiveness. In this paper, we present SparkAC, a novel access control mechanism for secure data sharing and analysis in Spark. In particular, we first propose a purpose-aware access control (PAAC) model, which introduces new concepts of data processing purpose and data operation purpose and an automatic purpose analysis algorithm that identifies purposes from data analytics operations and queries. Moreover, we develop a unified access control mechanism that implements PAAC model in two modules. GuardSpark++ supports structured data access control in Spark Catalyst and GuardDAG supports unstructured data access control in Spark core. Finally, we evaluate GuardSpark++ and GuardDAG with multiple data sources, applications, and data analytics engines. Experimental results show that SparkAC provides effective access control functionalities with very small (GuardSpark++) or medium (GuardDAG) performance overhead
- 8 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 20 (2) , 1104-1123
SparkAC: Fine-Grained Access Control in Spark for Secure Data Sharing and Analytics
With the development of computing and communication technologies, an extremely large amount of data has been collected, stored, utilized, and shared, while new security and privacy challenges arise. Existing access control mechanisms provided by big data platforms have limitations in granularity and expressiveness. In this paper, we present SparkAC, a novel access control mechanism for secure data sharing and analysis in Spark. In particular, we first propose a purpose-aware access control (PAAC) model, which introduces new concepts of data processing purpose and data operation purpose and an automatic purpose analysis algorithm that identifies purposes from data analytics operations and queries. Moreover, we develop a unified access control mechanism that implements PAAC model in two modules. GuardSpark++ supports structured data access control in Spark Catalyst and GuardDAG supports unstructured data access control in Spark core. Finally, we evaluate GuardSpark++ and GuardDAG with multiple data sources, applications, and data analytics engines. Experimental results show that SparkAC provides effective access control functionalities with very small (GuardSpark++) or medium (GuardDAG) performance overhead